Skip to main content
Språkbanken Text is a department within Språkbanken.

7th NLP4CALL, SLTC, Stockholm, Sweden

SLTC workshop, Stockholm, Sweden, 7 November, 2018

 

Proceedings

  • The Linköping University Press workshop proceedings are now online: here
  • The ACL anthology proceedings are now available here

Thank you all for a wonderful workshop!


Venue

The NLP4CALL workshop is co-located with SLTC 2018 in Stockholm.
The workshop will be held in Aula Magna at Stockholm University’s Frescati campus. The room in Aula Magna is called Spelbomskan, but there will be signs showing you to the way inside the building. You can easily reach it by subway (station: Universitetet) or bus (line 50).

Aula Magna’s street address: Frescativägen 11 (map with directions)


Registration information

At least one author of the accepted papers should be registered for the workshop. In order to register, please go to this page and follow the instructions.
Please note that the early bird deadline has been extended to October 12!


Program

Room: TBD

Time Program point
09.00 - 09.30 Registration
09.30 - 09.40 Opening
Ildikó Pilán
09.40 - 10.40 Oral presentations (15 min + 5 min questions)
  Chair: Robert Östling
09.40 - 10.00 Margot Mieskes and Ulrike Pado.
Work Smart - Reducing Effort in Short-Answer Grading [PDF] [slides]
10.00 - 10.20 Inga Kempfert and Christine Köhn.
An Automatic Error Tagger for German [PDF] [slides]
10.20 - 10.40 Gerold Schneider and Johannes Graën.
NLP Corpus Observatory - Looking for Constellations in Parallel Corpora to Improve Learners' Collocational Skills [PDF] [slides]
10.40 - 11.00 Coffee break
11.00 - 11.20 Oral presentation 4 (15 min + 5 min questions)
  Chair: Peter Ljunglöf
  Adriane Boyd.
Normalization in Context: Inter-Annotator Agreement for Meaning-Based Target Hypothesis Annotation [PDF] [slides]
11.20 - 12.10 Invited talk (40 min + 10 min questions)
  Jill Burstein
Natural Language Processing for Education: Applications for Reading and Writing Proficiency [slides]
12.15 - 13.30 Lunch
13.30 - 14.05 Lightning talks (5 min each)
  Chair: David Alfter
  Osama Hamed and Torsten Zesch.
The Role of Diacritics in Increasing the Difficulty of Arabic Lexical Recognition Tests [PDF]
  Zarah Weiss, Sabrina Dittrich and Detmar Meurers.
A Linguistically-Informed Search Engine to Identify Reading Material for Functional Illiteracy Classes [PDF]
  Lene Antonsen and Chiara Argese.
Using authentic texts for grammar exercises for a minority language [PDF]
  Herbert Lange and Peter Ljunglöf.
Demonstrating the MUSTE Language Learning Environment [PDF]
  Ramon Ziai, Bjoern Rudzewitz, Kordula De Kuthy, Florian Nuxoll and Detmar Meurers.
Feedback Strategies for Form and Meaning in a Real-life Language Tutoring System [PDF]
  Beáta Megyesi, Sofia Johansson, Dan Rosén, Carl-Johan Schenström, Gunlög Sundberg, Mats Wirén and Elena Volodina, .
Learner Corpus Anonymization in the Age of GDPR: Insights from the Creation of a Learner Corpus of Swedish [PDF]
14.10 - 15.30 Poster session (Poster size: 125cm (width) x 150 cm (height))
15.00 - 15.30 Coffee break
15.30 - 16.20 Invited talk (40 min + 10 min questions)
  Chair: Therese Lindström Tiedemann
  Jan Hulstijn
Usage-based views on second language acquisition and the Common European Framework of Reference (CEFR): their potential relevance for the NLP field [slides]
16.20 - 16.30 Closing
Elena Volodina
17.00 Welcome reception


Invited speakers

Jill Burstein, ETS

Jill Burstein is a Research Director of the Natural Language Processing Group in Research & Development at Educational Testing Service in Princeton, New Jersey. Her research interests span Natural Language Processing for educational technology, automated essay scoring and evaluation, discourse and sentiment analysis, argumentation mining, education policy, English language learning, and writing research. The intersection of her interests has led to two extensively used commercial applications for English L2 learners: E-rater®, ETS' automated essay evaluation application, and the Language Muse Activity PaletteTM -- a new classroom tool under development targeting English learners that automatically generates language activities for classroom texts to support content comprehension. Jill Burstein is one of the most successful researchers within ICALL that together with a group of bright researchers made ICALL tools a reality for many teachers of L2 English.

Title: Natural Language Processing for Education: Applications for Reading and Writing Proficiency

Automated writing evaluation (or, AWE) systems have been largely used to support the measurement of writing skills for on-demand, large-volume, high-stakes assessments. Advances in natural language processing (NLP)-driven AWE now affords the ability, in real-time, to generate a variety of linguistic information which can provide support literacy for reading and writing. NLP-based technology can now be used to 1) build a broader array of capabilities to support the instruction for a diverse population of learners, and 2) offer educational analytics for various stakeholders, including students, instructors, parents, administrators and policy-makers. This talk will discuss the history of AWE, the literacy-based motivation and trajectory for AWE-driven technology development, two technology use cases of AWE-based reading (The Language Muse® Activity Palette) and writing applications (The Writing Mentor™), and exploratory research examining relationships between linguistic features in college writing and broader success predictors that can potentially inform continued development of technology that supports literacy.

 

Jan Hulstijn, UVA

Jan Hulstijn is professor emeritus of second language acquisition at the Amsterdam Center for Language and Communication (ACLC) of the University of Amsterdam. He has been affiliated with this university (full professor) since 1998. Before that he held positions at Leiden University and the Free University of Amsterdam. He was associate post-doc researcher at the University of Toronto, Canada (1982-1983) and he was visiting professor at the University of Leuven, Belgium, (2002) and at Stockholm University (2005). His main research interests are concerned with (1) language proficiency in native and non-native speakers; (2) explicit versus implicit accounts of first and second language learning and (3) theories of second language acquisition and philosophy of science. With others PIs, he received a number of research grants from the Netherlands Organisation of Scientific Research (NWO) between 1982 and 2007 (see webpage). In 2018 he received the 2018 distinguished scholar award from the European Second Language Association (EuroSLA) (http://www.eurosla.org/distinguished-scholar-award-2018-jan-h-hulstijn/). In 2015, he published a book presenting his theory of basic language cognition (BLC). His publication list can be downloaded from his webpage: http://www.uva.nl/profile/j.h.hulstijn.

Title: Usage-based views on second language acquisition and the Common European Framework of Reference (CEFR): their potential relevance for the NLP field

The first wave of the Cognitive Revolution (1960 – 1985) was dominated by (1) the competence-performance distinction and Universal Grammar in generative linguistics, and by (2) notions of modularity and serial processing in psycholinguistics. These notions also dominated the scientific study of second language acquisition (SLA) at the time. In contrast, more recent work in SLA is increasingly being influenced by ideas which originated during the second wave of the Cognitive Revolution (1985 – the present), in particular usage-based linguistics, Emergentism and the Competition Model, Construction Grammar, Dynamic Systems Theory, implicit/statistical learning, and statistical learning in relation to corpus linguistics.

These developments might be important for people working in the field of NLP. In the first part of my talk I will give a brief overview of these more recent developments , with a particular focus on the unified conceptualization of representation and processing (referred to together with the term cognition), the notion of graded cognition (as opposed to dichotomous views of cognition), the notion of frequency and recency of linguistic elements in learners’ input (with the aid of corpus linguistics), the removal of traditional barriers between lexis and grammar, and the need to explain individual differences in language knowledge and use. In my view, current software for automatic analysis of corpora of spoken or written language production is still incapable of identifying grammatical constructions relevant from an SLA perspective. I will briefly introduce the notions of shared/basic and non-shared/extended language cognition (Hulstijn, 2015, 2018), which may also be useful for people in the NLP field. In the final part of my talk, I will present my views on the Common European Framework of Reference for Language (CEFR, 2001), which currently dominates almost all practices in second-language testing in Europe and increasingly in other parts of the world. There will be ample room for questions.

References:

Hulstijn, J. H. (2015). Language proficiency in native and non-native speakers: Theory and research. Amsterdam: John Benjamins Publishing Company.
Hulstijn, J.H. (2018, early view). An individual-differences framework for comparing non-native with native speakers: Perspectives from BLC Theory. Language Learning. DOI: 10.1111/lang.12317


Description of the workshop

The theme on Natural Language Processing (NLP) for Computer-Assisted Language Learning (NLP4CALL) is a meeting place for researchers working on the integration of Natural Language Processing and Speech Technologies in CALL systems and exploring the theoretical and methodological issues arising in this connection.

The intersection of Natural Language Processing and Speech/Dialogue Technology with Computer-Assisted Language Learning (CALL) brings “understanding” of language to CALL tools, thus making CALL intelligent. This fact has given the name for this area of research – Intelligent CALL, ICALL. As the definition suggests, apart from having excellent knowledge of Natural Language Processing and/or Speech/Dialogue Technology, ICALL researchers need good insights into the second language acquisition (SLA) theories and practices, as well as knowledge of second language pedagogy and didactics. This workshop invites therefore all ICALL-relevant research, including studies where NLP-enriched tools are used for testing SLA and pedagogical theories, and vice versa, where SLA theories/pedagogical practices are modeled in ICALL tools.

The workshop series on Natural Language Processing (NLP) for Computer-Assisted Language Learning (NLP4CALL) is a meeting place for researchers working on the integration of Natural Language Processing and Speech Technologies in CALL systems and exploring the theoretical and methodological issues arising in this connection.

The latter includes , among others, insights from Second Language Acquisition (SLA) research, on the one hand, and promote development of “Computational SLA” through setting up Second Language research infrastructure(s), on the other .

The intersection of Natural Language Processing (or Language Technology / Computational Linguistics) and Speech Technology with Computer-Assisted Language Learning (CALL) brings “understanding” of language to CALL tools, thus making CALL intelligent. This fact has given the name for this area of research – Intelligent CALL, ICALL. As the definition suggests, apart from having excellent knowledge of Natural Language Processing and/or Speech Technology, ICALL researchers need good insights into second language acquisition theories and practices, as well as knowledge of second language pedagogy and didactics. This workshop invites therefore a wide range of ICALL-relevant research, including studies where NLP-enriched tools are used for testing SLA and pedagogical theories, and vice versa, where SLA theories, pedagogical practices or empirical data are modeled in ICALL tools.

The NLP4CALL workshop series is aimed at bringing together competences from these areas for sharing experiences and brainstorming around the future of the field.

We welcome papers:

  • that describe research directly aimed at ICALL;
  • that demonstrate actual or discuss the potential use of existing Language and Speech Technologies or resources for language learning;
  • that describe the ongoing development of resources and tools with potential usage in ICALL, either directly in interactive applications, or indirectly in materials, application or curriculum development, e.g. learning material generation, assessment of learner texts/responses, individualized learning solutions, provision of feedback;
  • that discuss challenges and/or research agenda for ICALL;
  • that describe empirical studies on language learner data

A special focus is given to the established and upcoming infrastructures aimed at SLA and learner corpus research, covering questions such as data collection, legal issues, reliability of annotation, annotation tool development, search environments for SLA-relevant data, etc.

We encourage paper presentations and software demonstrations describing the above-mentioned themes primarily, but not exclusively, for the Nordic languages.


Submission information

We will be using NAACL 2018 template for the workshop this year.

Authors are invited to submit long papers (8-12 pages) alternatively short or demo papers (4-7 pages), page count not including references. Please indicate one relevant paper type at submission time. Only pdf files will be accepted. Submissions will be managed through the electronic conference management system EasyChair. Final camera-ready versions of accepted papers will be given an additional page to address reviewer comments.

Papers should describe original unpublished work or work-in-progress. Every paper will be reviewed by at least 2 members of the program committee. As reviewing will be blind, please ensure that papers are anonymous. Self-references that reveal the author's identity, e.g., "We previously showed (Smith, 1991) ...", should be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ...". Submissions will be judged on appropriateness, clarity, originality/innovativeness, correctness/soundness, meaningful comparison, significance and impact of ideas or results.

All accepted papers will be collected into a proceedings volume to be submitted for publication in the NEALT Proceeding Series (Linköping Electronic Conference Proceedings) and, additionally, double-published through ACL anthology, following experiences from previous workshops, e.g. the 6th NLP4CALL&LA.

For licensing reasons, all camera-ready papers should include the following sentence as an unmarked (unnumbered) footnote on the first page of the paper: This work is licensed under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/.


Important dates:

  • 21 June, Thursday: first call for papers
  • 15 August, Wednesday: second call for papers
  • 7 September, Friday: final call for papers
  • 18 September, Extended to: 24 September, Monday: paper submission deadline (long, short and demo)
  • 11 October, Thursday: notification of acceptance
  • 22 October, Monday: camera-ready papers for publication
  • 7 November, Wednesday: workshop date


Program committee:

  • Lars Ahrenberg, Linköping University, Sweden
  • David Alfter, University of Gothenburg, Sweden
  • Lisa Beinborn, University of Duisburg-Essen, Germany
  • Eckhard Bick, University of Southern Denmark, Denmark
  • Lars Borin, University of Gothenburg, Sweden
  • António Branco, University of Lisbon, Portugal
  • Jill Burstein, Educational Testing Services, US
  • Andrew Caines, University of Cambridge, UK
  • Dirk De Hertog, KU Leuven, Belgium
  • Simon Dobnik, University of Gothenburg, Sweden
  • Thomas François, UCLouvain, Belgium
  • Johannes Graën, University of Zurich, Switzerland
  • Andrea Horbach, University of Duisburg-Essen, Germany
  • John Lee, City University of Hong Kong, Hong Kong
  • Peter Ljunglöf, University of Gothenburg and Chalmers University of Technology, Sweden
  • Montse Maritxalar, University of the Basque country, Spain
  • Beáta Megyesi, Uppsala University, Sweden
  • Detmar Meurers, University of Tübingen, Germany
  • Martí Quixal, University of Tübingen, Germany
  • Robert Reynolds, Brigham Young University, USA
  • Gerold Schneider, University of Zurich, Switzerland
  • Irina Temnikova, Sofia University, Bulgaria
  • Francis Tyers, The Arctic University of Norway, Norway
  • Sowmya Vajjala, Iowa State University, US
  • Elena Volodina, University of Gothenburg, Sweden
  • Mats Wirén, Stockholm University, Sweden
  • Victoria Yaneva, University of Wolverhampton, UK
  • Torsten Zesch, University of Duisburg-Essen, Germany
  • Robert Östling, University of Helsinki, Finland


Workshop organizers

  • Ildikó Pilán, Språkbanken, Department of Swedish, University of Gothenburg; ildiko dot pilan at svenska dot gu dot se (Organizing chair)
  • Elena Volodina, Språkbanken, Department of Swedish, University of Gothenburg; elena dot volodina at svenska dot gu dot se
  • Lars Borin, Språkbanken, Department of Swedish, University of Gothenburg; lars dot borin at svenska dot gu dot se
  • David Alfter, Språkbanken, Department of Swedish, University of Gothenburg; david dot alfter at svenska dot gu dot se

This workshop follows a series of workshops on NLP for CALL organized by a Special Interest Group in Intelligent Computer-Assisted Language Learning (SIG-ICALL of NEALT). The workshop series has previously been financed by the Center for Language Technology at the University of Gothenburg.

We intend to continue this workshop series, which up to date has been the only ICALL-relevant recurring event based in the Nordic countries. Our intention is to co-locate the workshop series with the two major LT events in Scandinavia, SLTC and Nodalida, thus making this workshop an annual event. Through this workshop, we intend to profile ICALL research in Nordic countries and to provide a dissemination venue for researchers active in this area.


Related links

 

ICALL-related mailing lists

There are two mailing lists that spread ICALL-relevant information: one run by EuroCALL/CALICO SIG-ICALL group (nlpcall@artsservices.uwaterloo.ca // nlpcall@watarts.uwaterloo.ca) and the other one run by BEA-workshop organizers (bea.nlp.workshop@gmail.com). We encourage you to join them to be updated of the events, publications and discussions in the area

  • To join EuroCALL/CALICO list, contact Mathias Schulze (mschulze@uwaterloo.ca) . You can freely write to the EuroCALL/CALICO list when you want to disseminate some call for papers/information or ask questions.
  • To join BEA-list, contact Ekaterina Kochmar (Ekaterina.Kochmar@cl.cam.ac.uk) . BEA-mailing list spreads information in a digest form approx 4 times a year.

For NLP4CALL inquiries, please email Ildikó Pilán (ildiko dot pilan at svenska dot gu dot se)